If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊You can also buy me a Coffee ☕<a target="_blank" rel="ugc" href="https://emojipedia.org/hot-beverage"> </a>at <a target="_blank" rel="ugc" href="https://ko-fi.com/stickyricky">https://ko-fi.com/stickyricky</a>This model was trained using the collab/guide by holostrawberry <a target="_blank" rel="ugc" href="https://civarchive.com/models/22530/guide-make-your-own-loras-easy-and-free">[Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai</a><h3 id="heading-1473">About the artist:</h3>Twitter: <a target="_blank" rel="ugc" href="https://twitter.com/blushyspicy?lang=en">Blushy&amp;Spicy 💖🔥 (@BlushySpicy) / Twitter</a>Patreon: <a target="_blank" rel="ugc" href="https://www.patreon.com/blushyspicy">Blushy &amp; Spicy | Creating Pinups and Fun Content! | Patreon</a>Blushy &amp; Spicy make cute<a target="_blank" rel="ugc" href="https://twitter.com/blushyspicy?lang=en">💖</a> and the occassional nsfw <a target="_blank" rel="ugc" href="https://twitter.com/blushyspicy?lang=en">🔥</a> images. This model works for both. Pinups in particular are some of their main creations and therefore work well in this model.<h3 id="heading-1474">Weights &amp; Prompts</h3>The activation prompt is:<pre><code>blushyspicy</code></pre>LoCon:Most anime models are based on NAI. For those this should be your goto version.Use a weight of 1.0, adjust to taste. Check the example XYZ plot for reference.This version is also closer to blushy than spicy - it is less likely to create nsfw images unprompted.LoRA:Use a weight of 1.0. Go a bit lower (I used 0.9) for character loras. As usual I have included an XYZ plots for reference. Including "artist name" in the negative prompt is advised.For backgrounds and landscapes the model is generally low on details but when prompted for explicitly it tends towards brighter colors and blurring objects out of focus. Check out the two image sets with and without the model.Please leave a review if you enjoyed this model or have problems with it. I'd also be interested in how the model behaves with other base checkpoints, so why don't you give it a try and throw some images down below! 👇

BlushySpicy - Artist Style (LoRA/Lycoris)

Trained on the same dataset with a slower learning rate of 3e-4

blushyspicy-32.safetensors

LoCon (NAI)

LoRA (AOM)

imported from: <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/81762/blushyspicy-artist-style-loralycoris">https://civitai.com/models/81762/blushyspicy-artist-style-loralycoris</a>

Files with SHA256: d86d8fdd8b64178e0e974c3b4736799ee380b1198b2406075723ef4debd5cf8a